# tensorflow::ops::Conv2DBackpropFilter

`#include <nn_ops.h>`

Computes the gradients of convolution with respect to the filter.

## Summary

Args:

- scope: A [Scope](https://www.tensorflow.org/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object
- input: 4-D with shape `[batch, in_height, in_width, in_channels]`.
- filter_sizes: An integer vector representing the tensor shape of `filter`, where `filter` is a 4-D `[filter_height, filter_width, in_channels, out_channels]` tensor.
- out_backprop: 4-D with shape `[batch, out_height, out_width, out_channels]`. Gradients w.r.t. the output of the convolution.
- strides: The stride of the sliding window for each dimension of the input of the convolution. Must be in the same order as the dimension specified with format.
- padding: The type of padding algorithm to use.

<br />

Optional attributes (see `https://www.tensorflow.org/api_docs/cc/struct/tensorflow/ops/conv2-d-backprop-filter/attrs#structtensorflow_1_1ops_1_1_conv2_d_backprop_filter_1_1_attrs`):

- explicit_paddings: If `padding` is `"EXPLICIT"`, the list of explicit padding amounts. For the ith dimension, the amount of padding inserted before and after the dimension is `explicit_paddings[2 * i]` and `explicit_paddings[2 * i + 1]`, respectively. If `padding` is not `"EXPLICIT"`, `explicit_paddings` must be empty.
- data_format: Specify the data format of the input and output data. With the default format "NHWC", the data is stored in the order of: \[batch, in_height, in_width, in_channels\]. Alternatively, the format could be "NCHW", the data storage order of: \[batch, in_channels, in_height, in_width\].
- dilations: 1-D tensor of length 4. The dilation factor for each dimension of `input`. If set to k \> 1, there will be k-1 skipped cells between each filter element on that dimension. The dimension order is determined by the value of `data_format`, see above for details. Dilations in the batch and depth dimensions must be 1.

<br />

Returns:

- `https://www.tensorflow.org/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output`: 4-D with shape `[filter_height, filter_width, in_channels, out_channels]`. Gradient w.r.t. the `filter` input of the convolution.

<br />

| ### Constructors and Destructors ||
|---|---|
| `https://www.tensorflow.org/api_docs/cc/class/tensorflow/ops/conv2-d-backprop-filter#classtensorflow_1_1ops_1_1_conv2_d_backprop_filter_1a799b52a54b6ed6387afe8c2147aff0da(const ::https://www.tensorflow.org/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope & scope, ::https://www.tensorflow.org/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input input, ::https://www.tensorflow.org/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input filter_sizes, ::https://www.tensorflow.org/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input out_backprop, const gtl::ArraySlice< int > & strides, StringPiece padding)` ||
| `https://www.tensorflow.org/api_docs/cc/class/tensorflow/ops/conv2-d-backprop-filter#classtensorflow_1_1ops_1_1_conv2_d_backprop_filter_1a7bec0a5bc85d2c452e02c02feaa30bec(const ::https://www.tensorflow.org/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope & scope, ::https://www.tensorflow.org/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input input, ::https://www.tensorflow.org/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input filter_sizes, ::https://www.tensorflow.org/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input out_backprop, const gtl::ArraySlice< int > & strides, StringPiece padding, const https://www.tensorflow.org/api_docs/cc/struct/tensorflow/ops/conv2-d-backprop-filter/attrs#structtensorflow_1_1ops_1_1_conv2_d_backprop_filter_1_1_attrs & attrs)` ||

| ### Public attributes ||
|---|---|
| `https://www.tensorflow.org/api_docs/cc/class/tensorflow/ops/conv2-d-backprop-filter#classtensorflow_1_1ops_1_1_conv2_d_backprop_filter_1a627aac02d2a36f95929e36f2027c8672` | `https://www.tensorflow.org/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation` |
| `https://www.tensorflow.org/api_docs/cc/class/tensorflow/ops/conv2-d-backprop-filter#classtensorflow_1_1ops_1_1_conv2_d_backprop_filter_1aefc74eafda94631873fa7b35fb79bb9c` | `::https://www.tensorflow.org/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output` |

| ### Public functions ||
|---|---|
| `https://www.tensorflow.org/api_docs/cc/class/tensorflow/ops/conv2-d-backprop-filter#classtensorflow_1_1ops_1_1_conv2_d_backprop_filter_1aaae19666c83ef2abfd5d2b10b9cc1b79() const ` | `::tensorflow::Node *` |
| `https://www.tensorflow.org/api_docs/cc/class/tensorflow/ops/conv2-d-backprop-filter#classtensorflow_1_1ops_1_1_conv2_d_backprop_filter_1a24db1aa2b5b3fb8b00b8939b1708eb9c() const ` |   |
| `https://www.tensorflow.org/api_docs/cc/class/tensorflow/ops/conv2-d-backprop-filter#classtensorflow_1_1ops_1_1_conv2_d_backprop_filter_1a6cd0bf5f17fa87c8a484ea9288ce4a05() const ` |   |

| ### Public static functions ||
|---|---|
| `https://www.tensorflow.org/api_docs/cc/class/tensorflow/ops/conv2-d-backprop-filter#classtensorflow_1_1ops_1_1_conv2_d_backprop_filter_1a67e760b8ede5ea02dac7dee92c21a4c7(StringPiece x)` | `https://www.tensorflow.org/api_docs/cc/struct/tensorflow/ops/conv2-d-backprop-filter/attrs#structtensorflow_1_1ops_1_1_conv2_d_backprop_filter_1_1_attrs` |
| `https://www.tensorflow.org/api_docs/cc/class/tensorflow/ops/conv2-d-backprop-filter#classtensorflow_1_1ops_1_1_conv2_d_backprop_filter_1aa2179fd147f84ae7f11f6f1764b222db(const gtl::ArraySlice< int > & x)` | `https://www.tensorflow.org/api_docs/cc/struct/tensorflow/ops/conv2-d-backprop-filter/attrs#structtensorflow_1_1ops_1_1_conv2_d_backprop_filter_1_1_attrs` |
| `https://www.tensorflow.org/api_docs/cc/class/tensorflow/ops/conv2-d-backprop-filter#classtensorflow_1_1ops_1_1_conv2_d_backprop_filter_1a737b3cc66404da9e6005481ea4e794d3(const gtl::ArraySlice< int > & x)` | `https://www.tensorflow.org/api_docs/cc/struct/tensorflow/ops/conv2-d-backprop-filter/attrs#structtensorflow_1_1ops_1_1_conv2_d_backprop_filter_1_1_attrs` |
| `https://www.tensorflow.org/api_docs/cc/class/tensorflow/ops/conv2-d-backprop-filter#classtensorflow_1_1ops_1_1_conv2_d_backprop_filter_1a953aaf76215ad6a39ef6ca399022357c(bool x)` | `https://www.tensorflow.org/api_docs/cc/struct/tensorflow/ops/conv2-d-backprop-filter/attrs#structtensorflow_1_1ops_1_1_conv2_d_backprop_filter_1_1_attrs` |

| ### Structs ||
|---|---|
| [tensorflow::ops::Conv2DBackpropFilter::Attrs](https://www.tensorflow.org/api_docs/cc/struct/tensorflow/ops/conv2-d-backprop-filter/attrs) | Optional attribute setters for [Conv2DBackpropFilter](https://www.tensorflow.org/api_docs/cc/class/tensorflow/ops/conv2-d-backprop-filter#classtensorflow_1_1ops_1_1_conv2_d_backprop_filter). |

## Public attributes

### operation

```
Operation operation
```

### output

```
::tensorflow::Output output
```

## Public functions

### Conv2DBackpropFilter

```
 Conv2DBackpropFilter(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input,
  ::tensorflow::Input filter_sizes,
  ::tensorflow::Input out_backprop,
  const gtl::ArraySlice< int > & strides,
  StringPiece padding
)
```

### Conv2DBackpropFilter

```
 Conv2DBackpropFilter(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input,
  ::tensorflow::Input filter_sizes,
  ::tensorflow::Input out_backprop,
  const gtl::ArraySlice< int > & strides,
  StringPiece padding,
  const Conv2DBackpropFilter::Attrs & attrs
)
```

### node

```
::tensorflow::Node * node() const 
```

### operator::tensorflow::Input

```
 operator::tensorflow::Input() const 
```

### operator::tensorflow::Output

```
 operator::tensorflow::Output() const 
```

## Public static functions

### DataFormat

```
Attrs DataFormat(
  StringPiece x
)
```

### Dilations

```
Attrs Dilations(
  const gtl::ArraySlice< int > & x
)
```

### ExplicitPaddings

```
Attrs ExplicitPaddings(
  const gtl::ArraySlice< int > & x
)
```

### UseCudnnOnGpu

```
Attrs UseCudnnOnGpu(
  bool x
)
```